apps/docs/docs/update-notes/v3.36.10.mdx
This release adds the Gemini 3 Flash preview model to more providers, improves DeepSeek reasoner “thinking” behavior during tool use, and fixes a context token-count display issue.
The gemini-3-flash-preview model is now available in the Roo Code Cloud provider, Google Gemini, GCP Vertex AI, Requesty, and OpenRouter providers. It’s the latest model from Google, released this morning (thanks contributors!) (#10151).
The DeepSeek provider’s deepseek-reasoner model now supports “interleaved thinking” and native tool calling. In our internal evals, tool calling succeeded 100% of the time, and the extended-run score improved to 93.4% (thanks zbww_!) (#9969, #10141).
~15.2.8 for improved compatibility with upstream fixes (#10140)